smarter_csv 1.0.7 → 1.0.8

checksums.yaml

@@ -0,0 +1,7 @@
+--- 
+SHA1: 
+  metadata.gz: 4426aea4be447cb000436980c4b8f34ac12d9683
+  data.tar.gz: 5f15ed8a24db46241f02e672d099413445011238
+SHA512: 
+  metadata.gz: fbf06328d2e51caa2e66ba913b7a6b49d0db4d37caf932a7f66846db3a47207adc066be4d7df65c6b215bf20f3d6d5713f85b0c1e3e5cd1f930ca573949c69ff
+  data.tar.gz: e098866b5d33c254136854853f5bd55bac89bcae93f286365518986a4d254d17ea116004a5367c5538a8dab6d8854bd6383109aac2889b503c20f86cc47c8f84

data/README.md

@@ -152,6 +152,9 @@ The options and the block are optional.
      |                             |          | Important if the file does not contain headers,                                      |
      |                             |          | otherwise you would lose the first line of data.                                     |
      | :file_encoding              |   utf-8  | Set the file encoding eg.: 'windows-1252' or 'iso-8859-1'                            |
+     | :force_simple_split         |   false  | force simiple splitting on :col_sep character for non-standard CSV-files.            |
+     |                             |          | e.g. when :quote_char is not properly escaped                                        |
+     | :verbose                    |   false  | print out line number while processing (to track down problems in input files)       |
 
 
 #### NOTES about CSV Headers:
@@ -197,6 +200,13 @@ Or install it yourself as:
 
 ## Changes
 
+#### 1.0.8 (2013-06-01)
+
+ * bugfix : fixed issue with nil values in inputs with quote-char (thanks to Félix Bellanger)
+ * new options:
+    * :force_simple_split : to force simiple splitting on :col_sep character for non-standard CSV-files. e.g. without properly escaped :quote_char
+    * :verbose : print out line number while processing (to track down problems in input files)
+
 #### 1.0.7 (2013-05-20)
 
  * allowing process to work with objects with a 'readline' method (thanks to taq)
@@ -263,6 +273,7 @@ And a special thanks to those who contributed pull requests:
  * [Martin Nilsson](http://github.com/MrTin) 
  * [Eustáquio Rangel](http://github.com/taq) 
  * [Pavel](http://github.com/paxa) 
+ * [Félix Bellanger](https://github.com/Keeguon)
 
 
 ## Contributing

data/lib/smarter_csv/smarter_csv.rb

@@ -4,7 +4,7 @@ module SmarterCSV
   end
 
   def SmarterCSV.process(input, options={}, &block)   # first parameter: filename or input object with readline method
-    default_options = {:col_sep => ',' , :row_sep => $/ , :quote_char => '"',
+    default_options = {:col_sep => ',' , :row_sep => $/ , :quote_char => '"', :force_simple_split => false , :verbose => false ,
       :remove_empty_values => true, :remove_zero_values => false , :remove_values_matching => nil , :remove_empty_hashes => true , :strip_whitespace => true, 
       :convert_values_to_numeric => true, :strip_chars_from_headers => nil , :user_provided_headers => nil , :headers_in_file => true,
       :comment_regexp => /^#/, :chunk_size => nil , :key_mapping_hash => nil , :downcase_header => true, :strings_as_keys => false, :file_encoding => 'utf-8'
@@ -13,6 +13,7 @@ module SmarterCSV
     headerA = []
     result = []
     old_row_sep = $/
+    line_count = 0
     begin
       $/ = options[:row_sep]
       f = input.respond_to?(:readline) ? input : File.open(input, "r:#{options[:file_encoding]}")
@@ -21,9 +22,10 @@ module SmarterCSV
         # process the header line in the CSV file..
         # the first line of a CSV file contains the header .. it might be commented out, so we need to read it anyhow
         header = f.readline.sub(options[:comment_regexp],'').chomp(options[:row_sep])
+        line_count += 1
         header = header.gsub(options[:strip_chars_from_headers], '') if options[:strip_chars_from_headers]
-        if header =~ %r{#{options[:quote_char]}}
-          file_headerA = CSV.parse( header ).flatten
+        if (header =~ %r{#{options[:quote_char]}}) and (! options[:force_simple_split])
+          file_headerA = CSV.parse( header ).flatten.collect!{|x| x.nil? ? '' : x} # to deal with nil values from CSV.parse
         else
           file_headerA =  header.split(options[:col_sep])
         end
@@ -71,11 +73,13 @@ module SmarterCSV
       # now on to processing all the rest of the lines in the CSV file:
       while ! f.eof?    # we can't use f.readlines() here, because this would read the whole file into memory at once, and eof => true
         line = f.readline  # read one line.. this uses the input_record_separator $/ which we set previously!
+        line_count += 1
+        print "processing line %10d\r" % line_count if options[:verbose]
         next  if  line =~ options[:comment_regexp]  # ignore all comment lines if there are any
         line.chomp!    # will use $/ which is set to options[:col_sep]
 
-        if line =~ %r{#{options[:quote_char]}}
-          dataA = CSV.parse( line ).flatten
+        if (line =~ %r{#{options[:quote_char]}}) and (! options[:force_simple_split])
+          dataA = CSV.parse( line ).flatten.collect!{|x| x.nil? ? '' : x} # to deal with nil values from CSV.parse
         else
           dataA =  line.split(options[:col_sep])
         end

data/lib/smarter_csv/version.rb

@@ -1,3 +1,3 @@
 module SmarterCSV
-  VERSION = "1.0.7"
+  VERSION = "1.0.8"
 end

metadata

@@ -1,29 +1,31 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification 
 name: smarter_csv
-version: !ruby/object:Gem::Version
-  version: 1.0.7
-  prerelease: 
+version: !ruby/object:Gem::Version 
+  version: 1.0.8
 platform: ruby
-authors:
-- ! 'Tilo Sloboda
+authors: 
+- |
+  Tilo Sloboda
 
-'
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-05-20 00:00:00.000000000 Z
+
+date: 2013-06-01 00:00:00 Z
 dependencies: []
-description: Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, with
-  optional features for processing large files in parallel, embedded comments, unusual
-  field- and record-separators, flexible mapping of CSV-headers to Hash-keys
-email:
-- ! 'tilo.sloboda@gmail.com
 
-'
+description: Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, with optional features for processing large files in parallel, embedded comments, unusual field- and record-separators, flexible mapping of CSV-headers to Hash-keys
+email: 
+- |
+  tilo.sloboda@gmail.com
+
 executables: []
+
 extensions: []
+
 extra_rdoc_files: []
-files:
+
+files: 
 - .gitignore
 - .rvmrc
 - Gemfile
@@ -37,28 +39,29 @@ files:
 - smarter_csv.gemspec
 homepage: https://github.com/tilo/smarter_csv
 licenses: []
+
+metadata: {}
+
 post_install_message: 
 rdoc_options: []
-require_paths:
+
+require_paths: 
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
-required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
-requirements:
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - &id001 
+    - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - *id001
+requirements: 
 - csv
 rubyforge_project: 
-rubygems_version: 1.8.15
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
-summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots
-  of optional features, e.g. chunked processing for huge CSV files
+specification_version: 4
+summary: Ruby Gem for smarter importing of CSV Files (and CSV-like files), with lots of optional features, e.g. chunked processing for huge CSV files
 test_files: []
+